competitive-ads-extractor

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • No Code (SAFE): The skill consists entirely of markdown instructions and metadata. No scripts (Python, JavaScript) or configuration files for package managers were provided for analysis.
  • Indirect Prompt Injection (LOW): The skill is designed to ingest and analyze untrusted external data (ad copy and creative from social media libraries). This creates a surface where an attacker could place malicious instructions in an ad to influence the agent's behavior.
  • Evidence for Indirect Prompt Injection: 1. Ingestion points: Facebook Ad Library, LinkedIn, and other ad platforms. 2. Boundary markers: None identified in the provided instructions. 3. Capability inventory: The skill describes capabilities for network access (scraping) and file writing (saving screenshots and reports). 4. Sanitization: No explicit sanitization or filtering of the ingested ad content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 03:09 PM